Evaluation

ConSpliceML on MLH1 curated clinical splicing variants

Published comparison; transcribed, not reproduced.

Research readiness

These checks assess whether the evidence supports a reproducible investigation. A source-checked score alone does not meet these requirements.

Release 2026-10-10-6e93f504adfc · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
artifact hashes: verification is missing
join integrity: verification is missing
score semantics: verification is missing
metric replay: verification is missing

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
artifact hashes: verification is missing
join integrity: verification is missing
score semantics: verification is missing
metric replay: verification is missing
annotations: verification is missing
dependence: verification is missing

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
artifact hashes: verification is missing
join integrity: verification is missing
score semantics: verification is missing
recipe pinned: verification is missing
resource estimate: verification is missing

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
artifact hashes: verification is missing
join integrity: verification is missing
score semantics: verification is missing
independent validation: verification is missing
overlap checked: verification is missing

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Read reviewed discrepancy investigations

Evaluation results

1 evaluation · 4 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: ConSpliceML (Smith and Kitzman 2023)	Protocol: MLH1 curated clinical splicing variants: transcriptome-normalised sensitivity at a 10% background call rate (Smith and Kitzman Table S2) Dataset: MLH1 curated clinical splicing variants (Smith and Kitzman benchmark set)	0.931 recall fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ConSpliceML on MLH1 curated clinical splicing variants splicing-follow-up-20261009-protocol-smith2023-mlh1-curated-tn10 Aggregation: Not reported Benchmarking splice variant prediction algorithms using massively parallel splicing assays; Smith and Kitzman 2023, Additional file 3 (Table S2) · Additional file 3 sheet 'Sensitivity 10% SDV', cell D9; row ConSpliceML, column MLH1
Configuration: ConSpliceML (Smith and Kitzman 2023)	Protocol: MLH1 curated clinical splicing variants: transcriptome-normalised sensitivity at a 10% background call rate (Smith and Kitzman Table S2) Dataset: MLH1 curated clinical splicing variants (Smith and Kitzman benchmark set)	0.816 recall fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ConSpliceML on MLH1 curated clinical splicing variants splicing-follow-up-20261009-protocol-smith2023-mlh1-curated-tn10 Aggregation: Not reported Benchmarking splice variant prediction algorithms using massively parallel splicing assays; Smith and Kitzman 2023, Additional file 3 (Table S2) · Additional file 3 sheet 'Sensitivity 10% SDV', cell D17; row Exon_ConSpliceML, column MLH1
Configuration: ConSpliceML (Smith and Kitzman 2023)	Protocol: MLH1 curated clinical splicing variants: transcriptome-normalised sensitivity at a 10% background call rate (Smith and Kitzman Table S2) Dataset: MLH1 curated clinical splicing variants (Smith and Kitzman benchmark set)	0.982 recall fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ConSpliceML on MLH1 curated clinical splicing variants splicing-follow-up-20261009-protocol-smith2023-mlh1-curated-tn10 Aggregation: Not reported Benchmarking splice variant prediction algorithms using massively parallel splicing assays; Smith and Kitzman 2023, Additional file 3 (Table S2) · Additional file 3 sheet 'Sensitivity 10% SDV', cell D25; row Intron_ConSpliceML, column MLH1
Configuration: ConSpliceML (Smith and Kitzman 2023)	Protocol: MLH1 curated clinical splicing variants: transcriptome-normalised sensitivity at a 10% background call rate (Smith and Kitzman Table S2) Dataset: MLH1 curated clinical splicing variants (Smith and Kitzman benchmark set)	0.931 recall fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ConSpliceML on MLH1 curated clinical splicing variants splicing-follow-up-20261009-protocol-smith2023-mlh1-curated-tn10 Aggregation: Not reported Benchmarking splice variant prediction algorithms using massively parallel splicing assays; Smith and Kitzman 2023, Additional file 3 (Table S2) · Additional file 3 sheet 'Sensitivity 10% SDV', cell D33; row Intron_NonCanon_ConSpliceML, column MLH1

Source checking is not independent reproduction. Release 2026-10-10-6e93f504adfc.

Evaluation procedure

splicing-follow-up-20261009-protocol-smith2023-mlh1-curated-tn10

Configuration: ConSpliceML (Smith and Kitzman 2023)
Protocol: MLH1 curated clinical splicing variants: transcriptome-normalised sensitivity at a 10% background call rate (Smith and Kitzman Table S2)
Dataset: MLH1 curated clinical splicing variants (Smith and Kitzman benchmark set)

origin: Independent external evaluation
configuration: Primary source as retrieved 2026-10-09
dataset version: Smith and Kitzman benchmark set (Additional file 2)
split: No split
population: 296 MLH1 single-base substitutions curated from 77 publications, with splicing supported by patient blood RNA RT-PCR or minigene analysis; essential splice-site variants from Lynch syndrome patients included without molecular evidence; 160 splice-disruptive.
inputs: SNV in genomic context with one MANE Select canonical transcript (SQUIRLS: default hg19 Ensembl)
adaptation: None; published models or precomputed scores
metric implementation: Sensitivity at the tool threshold calling 10% of the 500,000-SNV background set
aggregation: Pooled over the dataset's variants, by variant class
budget: Not reported
protocol id: splicing-follow-up-20261009-protocol-smith2023-mlh1-curated-tn10

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split: No split
Adaptation: None; published models or precomputed scores
Scoring implementation: Sensitivity at the tool threshold calling 10% of the 500,000-SNV background set

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

36 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-10-6e93f504adfc
Property and statement	Original source and location	Review and provenance
attributes.comparison.adaptation None; published models or precomputed scores Context-only references	Benchmarking splice variant prediction algorithms using massively parallel splicing assays Original source ↗ Additional file 3 sheet 'Sensitivity 10% SDV', column D ('MLH1'), rows for ConSpliceML Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Genome Biology 24:294, published 2023-12-21; PMC10734170 full-text XML Retrieved: 2026-10-09T20:49:26Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.adaptation` Source artifact SHA-256: `5aceff067af63ab59400ade7dd7db563a16fc7f4d6db6fa55d5b34689f7a0769` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.comparison.adaptation None; published models or precomputed scores Context-only references	Smith and Kitzman 2023, Additional file 3 (Table S2) Original source ↗ Additional file 3 sheet 'Sensitivity 10% SDV', column D ('MLH1'), rows for ConSpliceML Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 13059_2023_3144_MOESM3_ESM.xlsx inside the Europe PMC supplementaryFiles zip for PMC10734170 Retrieved: 2026-10-09T20:49:34Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.adaptation` Source artifact SHA-256: `c5ed8dc1488f87a1aff766c0ed4c8b3faab148259ca6e6f28e729b9a57a700fa` Hash scope: SHA-256 of the MOESM3 xlsx member (zip SHA-256 e06758da73eda5d4ba9c61361514ed2d84573bf50df5bf8036102389e019d525; Europe PMC assembles the zip per request). Inspected artifact
attributes.comparison.aggregation Pooled over the dataset's variants, by variant class Context-only references	Benchmarking splice variant prediction algorithms using massively parallel splicing assays Original source ↗ Additional file 3 sheet 'Sensitivity 10% SDV', column D ('MLH1'), rows for ConSpliceML Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Genome Biology 24:294, published 2023-12-21; PMC10734170 full-text XML Retrieved: 2026-10-09T20:49:26Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `5aceff067af63ab59400ade7dd7db563a16fc7f4d6db6fa55d5b34689f7a0769` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.comparison.aggregation Pooled over the dataset's variants, by variant class Context-only references	Smith and Kitzman 2023, Additional file 3 (Table S2) Original source ↗ Additional file 3 sheet 'Sensitivity 10% SDV', column D ('MLH1'), rows for ConSpliceML Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 13059_2023_3144_MOESM3_ESM.xlsx inside the Europe PMC supplementaryFiles zip for PMC10734170 Retrieved: 2026-10-09T20:49:34Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `c5ed8dc1488f87a1aff766c0ed4c8b3faab148259ca6e6f28e729b9a57a700fa` Hash scope: SHA-256 of the MOESM3 xlsx member (zip SHA-256 e06758da73eda5d4ba9c61361514ed2d84573bf50df5bf8036102389e019d525; Europe PMC assembles the zip per request). Inspected artifact
attributes.comparison.budget Not reported Context-only references	Benchmarking splice variant prediction algorithms using massively parallel splicing assays Original source ↗ Additional file 3 sheet 'Sensitivity 10% SDV', column D ('MLH1'), rows for ConSpliceML Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Genome Biology 24:294, published 2023-12-21; PMC10734170 full-text XML Retrieved: 2026-10-09T20:49:26Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `5aceff067af63ab59400ade7dd7db563a16fc7f4d6db6fa55d5b34689f7a0769` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.comparison.budget Not reported Context-only references	Smith and Kitzman 2023, Additional file 3 (Table S2) Original source ↗ Additional file 3 sheet 'Sensitivity 10% SDV', column D ('MLH1'), rows for ConSpliceML Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 13059_2023_3144_MOESM3_ESM.xlsx inside the Europe PMC supplementaryFiles zip for PMC10734170 Retrieved: 2026-10-09T20:49:34Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `c5ed8dc1488f87a1aff766c0ed4c8b3faab148259ca6e6f28e729b9a57a700fa` Hash scope: SHA-256 of the MOESM3 xlsx member (zip SHA-256 e06758da73eda5d4ba9c61361514ed2d84573bf50df5bf8036102389e019d525; Europe PMC assembles the zip per request). Inspected artifact
attributes.comparison.dataset_version Smith and Kitzman benchmark set (Additional file 2) Context-only references	Benchmarking splice variant prediction algorithms using massively parallel splicing assays Original source ↗ Additional file 3 sheet 'Sensitivity 10% SDV', column D ('MLH1'), rows for ConSpliceML Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Genome Biology 24:294, published 2023-12-21; PMC10734170 full-text XML Retrieved: 2026-10-09T20:49:26Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.dataset_version` Source artifact SHA-256: `5aceff067af63ab59400ade7dd7db563a16fc7f4d6db6fa55d5b34689f7a0769` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.comparison.dataset_version Smith and Kitzman benchmark set (Additional file 2) Context-only references	Smith and Kitzman 2023, Additional file 3 (Table S2) Original source ↗ Additional file 3 sheet 'Sensitivity 10% SDV', column D ('MLH1'), rows for ConSpliceML Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 13059_2023_3144_MOESM3_ESM.xlsx inside the Europe PMC supplementaryFiles zip for PMC10734170 Retrieved: 2026-10-09T20:49:34Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.dataset_version` Source artifact SHA-256: `c5ed8dc1488f87a1aff766c0ed4c8b3faab148259ca6e6f28e729b9a57a700fa` Hash scope: SHA-256 of the MOESM3 xlsx member (zip SHA-256 e06758da73eda5d4ba9c61361514ed2d84573bf50df5bf8036102389e019d525; Europe PMC assembles the zip per request). Inspected artifact
attributes.comparison.inputs SNV in genomic context with one MANE Select canonical transcript (SQUIRLS: default hg19 Ensembl) Context-only references	Benchmarking splice variant prediction algorithms using massively parallel splicing assays Original source ↗ Additional file 3 sheet 'Sensitivity 10% SDV', column D ('MLH1'), rows for ConSpliceML Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Genome Biology 24:294, published 2023-12-21; PMC10734170 full-text XML Retrieved: 2026-10-09T20:49:26Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.inputs` Source artifact SHA-256: `5aceff067af63ab59400ade7dd7db563a16fc7f4d6db6fa55d5b34689f7a0769` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
attributes.comparison.inputs SNV in genomic context with one MANE Select canonical transcript (SQUIRLS: default hg19 Ensembl) Context-only references	Smith and Kitzman 2023, Additional file 3 (Table S2) Original source ↗ Additional file 3 sheet 'Sensitivity 10% SDV', column D ('MLH1'), rows for ConSpliceML Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 13059_2023_3144_MOESM3_ESM.xlsx inside the Europe PMC supplementaryFiles zip for PMC10734170 Retrieved: 2026-10-09T20:49:34Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.inputs` Source artifact SHA-256: `c5ed8dc1488f87a1aff766c0ed4c8b3faab148259ca6e6f28e729b9a57a700fa` Hash scope: SHA-256 of the MOESM3 xlsx member (zip SHA-256 e06758da73eda5d4ba9c61361514ed2d84573bf50df5bf8036102389e019d525; Europe PMC assembles the zip per request). Inspected artifact

All evidence (JSONL) (gzip)How to read the evidence

Sources and history

Release 2026-10-10-6e93f504adfc · Record review: source checked

2 source records and release history

Benchmarking splice variant prediction algorithms using massively parallel splicing assays · Original source · Genome Biology 24:294, published 2023-12-21; PMC10734170 full-text XML
Smith and Kitzman 2023, Additional file 3 (Table S2) · Original source · 13059_2023_3144_MOESM3_ESM.xlsx inside the Europe PMC supplementaryFiles zip for PMC10734170

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: splicing-follow-up-20261009-eval-smith2023-mlh1-curated-conspliceml

areas: dna-genomes
contexts: research
origin: independent_paper
protocol: splicing-follow-up-20261009-protocol-smith2023-mlh1-curated-tn10
version: Primary source as retrieved 2026-10-09
comparison: dataset version: Smith and Kitzman benchmark set (Additional file 2); split: No split; population: 296 MLH1 single-base substitutions curated from 77 publications, with splicing supported by patient blood RNA RT-PCR or minigene analysis; essential splice-site variants from Lynch syndrome patients included without molecular evidence; 160 splice-disruptive.; inputs: SNV in genomic context with one MANE Select canonical transcript (SQUIRLS: default hg19 Ensembl); adaptation: None; published models or precomputed scores; metric implementation: Sensitivity at the tool threshold calling 10% of the 500,000-SNV background set; aggregation: Pooled over the dataset's variants, by variant class; budget: Not reported; protocol id: splicing-follow-up-20261009-protocol-smith2023-mlh1-curated-tn10
source locator: Additional file 3 sheet 'Sensitivity 10% SDV', column D ('MLH1'), rows for ConSpliceML

Related records

system: ConSpliceML (Smith and Kitzman 2023)
assessment: MLH1 curated clinical splicing variants: transcriptome-normalised sensitivity at a 10% background call rate (Smith and Kitzman Table S2)
data: MLH1 curated clinical splicing variants (Smith and Kitzman benchmark set)
evaluation: smith2023-mlh1-curated-conspliceml-all recall
evaluation: smith2023-mlh1-curated-conspliceml-exon recall
evaluation: smith2023-mlh1-curated-conspliceml-intron recall
evaluation: smith2023-mlh1-curated-conspliceml-intron-noncanon recall

Suggest a correction